CN104715483B - The automatic division method of lung CT image abnormal area - Google Patents
The automatic division method of lung CT image abnormal area Download PDFInfo
- Publication number
- CN104715483B CN104715483B CN201510122955.9A CN201510122955A CN104715483B CN 104715483 B CN104715483 B CN 104715483B CN 201510122955 A CN201510122955 A CN 201510122955A CN 104715483 B CN104715483 B CN 104715483B
- Authority
- CN
- China
- Prior art keywords
- region
- pixel
- point
- pulmonary abnormalities
- pulmonary
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 27
- 210000004072 lung Anatomy 0.000 title claims abstract description 21
- 230000002685 pulmonary effect Effects 0.000 claims abstract description 77
- 230000005856 abnormality Effects 0.000 claims abstract description 70
- 230000011218 segmentation Effects 0.000 claims abstract description 46
- 238000010586 diagram Methods 0.000 description 6
- 239000005337 ground glass Substances 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 208000020816 lung neoplasm Diseases 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 2
- 238000004195 computer-aided diagnosis Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 description 2
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
- Image Processing (AREA)
Abstract
The automatic division method of lung CT image abnormal area provided by the invention, including:Each vertex neighborhood gradient minimum value is searched for by toboggan from pulmonary parenchyma CT images, the region of pulmonary abnormalities initial growth point is obtained according to neighborhood gradient minimum value, initial growth seed point is determined according to the region of pulmonary abnormalities initial growth point;Pixel grey scale constraint and growth distance restraint are obtained according to initial growth seed point, and constrains and grows in distance restraint from pixel grey scale and pulmonary abnormalities region is determined by region growing method;The border in each layer pulmonary abnormalities region is obtained according to pulmonary abnormalities region, and then obtain the boundary pixel point of the adjacent layer in the pulmonary abnormalities region on default direction, average distance difference is obtained by the boundary pixel point of adjacent layer and the central point in pulmonary abnormalities region, and the boundary pixel point for exceeding average distance difference to range difference in all boundary pixel points carries out smoothly obtaining the segmentation figure picture in pulmonary abnormalities region.
Description
Technical field
The present invention relates to image Segmentation Technology, more particularly to a kind of automatic segmentation side of lung CT image abnormal area
Method.
Background technology
The automatic segmentation of lung CT image abnormal tissue is a major issue of computer-aided diagnosis area research, it
The automatic acquisition of pulmonary abnormalities tissue can be completed, shortens stand-by period during clinical diagnosis, in computer-aided diagnosis field
There is important application value.
Lung CT image abnormal tissue according to abnormal position classification can be divided into isolated type, with angiosynizesis type and
With the type such as pleaural adhesion;It can be divided into the types such as ground glass shadow, Lung neoplasm and lung neoplasm according to abnormal species.Wherein, glass is ground
Glass shadow type is most to be difficult to split in pulmonary abnormalities.The existing pulmonary abnormalities tissue segmentation algorithm based on region growing all needs
Initial growth seed point is manually obtained, so as to cause inaccuracy.
The content of the invention
The automatic division method of lung CT image abnormal area provided by the invention, can accurately obtain pulmonary abnormalities area
The segmentation figure picture in domain.
According to an aspect of the present invention, there is provided a kind of automatic division method of lung CT image abnormal area, including:
Each vertex neighborhood gradient minimum value is searched for by toboggan from pulmonary parenchyma CT images, according to the neighborhood gradient most
Small value obtains the region of pulmonary abnormalities initial growth point, and is determined initially according to the region of the pulmonary abnormalities initial growth point
Grow seed point;Pixel grey scale constraint and growth distance restraint are obtained according to the initial growth seed point, and from the pixel
Pulmonary abnormalities region is determined in grayscale restraint and growth distance restraint;Region growing method is passed through according to the pulmonary abnormalities region
The border in each layer pulmonary abnormalities region is obtained, and then obtains the side of the adjacent layer in the pulmonary abnormalities region on default direction
Boundary's pixel, average departure deviation is obtained by the boundary pixel point of the adjacent layer and the central point in the pulmonary abnormalities region
Value, and the boundary pixel point for exceeding the average distance difference to range difference in all boundary pixel points carries out smoothly obtaining lung
The segmentation figure picture of abnormal area, wherein, the range difference is on the default direction, two in the pulmonary abnormalities region
The boundary pixel point of adjacent layer and the distance difference of the central point in the pulmonary abnormalities region.
The automatic division method of lung CT image abnormal area provided in an embodiment of the present invention, by according to initial growth kind
Son point obtains pixel grey scale constraint and growth distance restraint, and constrains and grow from pixel grey scale and determine that lung is different in distance restraint
Normal region, and pulmonary abnormalities region is smoothed, so as to accurately obtain the segmentation figure picture in pulmonary abnormalities region.
Brief description of the drawings
Fig. 1 is the automatic division method flow chart of lung CT image abnormal area provided in an embodiment of the present invention;
Fig. 2 is the pulmonary abnormalities area schematic of solid nodules type provided in an embodiment of the present invention;
Fig. 3 is the different segmentation result schematic diagrames of same isolation degree provided in an embodiment of the present invention;
Fig. 4 is the different segmentation result schematic diagrames of same ground glass exception provided in an embodiment of the present invention;
Fig. 5 is man-machine interactively number result schematic diagram when pulmonary abnormalities provided in an embodiment of the present invention segmentation is completed;
Fig. 6 is the segmentation result signal of the initial growth seed point under the conditions of different selections provided in an embodiment of the present invention
Figure.
Embodiment
The present general inventive concept is, by obtaining pixel grey scale constraint and growth distance about according to initial growth seed point
Beam, and constrain and grow in distance restraint from pixel grey scale and pulmonary abnormalities region is determined by region growing method, and to lung
Abnormal area is smoothed, so as to accurately obtain the segmentation figure picture in pulmonary abnormalities region.
The automatic division method of lung CT image abnormal area is described in detail below in conjunction with the accompanying drawings.
Fig. 1 is the automatic division method flow chart of lung CT image abnormal area provided in an embodiment of the present invention.
With reference to Fig. 1, in step S101, each vertex neighborhood gradient minimum is searched for by toboggan from pulmonary parenchyma CT images
Value, the region of pulmonary abnormalities initial growth point is obtained according to the neighborhood gradient minimum value, and according at the beginning of the pulmonary abnormalities
The region of beginning growing point determines initial growth seed point.
Here, the region of initial growth point can be the high bright part that downhill race marks image.
Step S101 detailed processes are as follows:The minimum ladder of neighborhood is carried out one by one firstly for each pixel of pulmonary parenchyma CT images
Angle value calculates, and searches for its neighborhood inside gradient minimum value, and sequentially store each pulmonary parenchyma pixel in construction gradient stack in advance
The gradient minimum value that point obtains;Secondly, the minimal gradient value obtained to each pixel afterwards, traversal gradient stack is with having stored
Each gradient minimum value compare, obtain one of mark value of the Grad most like with it as this on mark image,
And the element marking value on its mark image is calculated by formula (1):
LSource(i, j)=GSource(i, j) * p+ [SMax (ToboStack, GToboMin(i, j))]2*q (1)
GSource(i, j) is the source image vegetarian refreshments (i, j) that scans for, and ToboStack is the gradient stack of construction, GToboMin(i,
J) the neighborhood minimal gradient value obtained for search, SMax (ToboStack, GToboMin(i, j)) function representation searches in gradient stack
Rope and GToboMin(i, j) inner immediate Grad.LSource(i, j) represents that search source image vegetarian refreshments (i, j) marks image in downhill race
In element marking value.P, q represents weight by the Grad for determining to be calculated in source pixel Grad and gradient stack based on
Calculate LSourceThe proportion of (i, j).
In step S102, pixel grey scale constraint is obtained according to the initial growth seed point and grows distance restraint, and from
The pixel grey scale constraint and growth distance restraint determine pulmonary abnormalities region by region growing method.
In step S103, the border in each layer pulmonary abnormalities region is obtained according to the pulmonary abnormalities region, and then obtain
On default direction in the pulmonary abnormalities region adjacent layer boundary pixel point, by the boundary pixel point of the adjacent layer and
The central point in the pulmonary abnormalities region obtains average distance difference, and range difference in all boundary pixel points is exceeded described flat
The boundary pixel point of equal distance difference carries out smoothly obtaining the segmentation figure picture in pulmonary abnormalities region, wherein, the range difference for
On the default direction, the boundary pixel point of two adjacent layers and the pulmonary abnormalities region in the pulmonary abnormalities region
The distance difference of central point.
Here, a direction can be taken every 2 ° according to default direction, calculates each two adjacent layer in all directions
Abnormal area border and the distance difference of image center, will finally be carried out more than the pixel of mean difference by formula (2)
Smoothly.
Further, it is described that pixel grey scale constraint and growth distance restraint bag are obtained according to the initial growth seed point
Include:
The threshold value of abnormal area pixel value is determined according to the gray value of the initial growth seed point, and according to the exception
The threshold value of area pixel value obtains the pixel grey scale constraint, and
The growth distance restraint is determined according to the region of the pulmonary abnormalities initial growth point.
Further, constrain and grow in distance restraint from the pixel grey scale and determine that lung is different by region growing method
Normal region includes:
Constrain and grow in distance restraint from the pixel grey scale and lung abnormal area pixel is obtained by region growing method
Point;
Corresponding algebraically mark is assigned to each pixel of the lung abnormal area;
Marked according to the algebraically and determine the pulmonary abnormalities region.
Further, the method further includes:
If the numerical value of the pixel of the first generation and the pulmonary abnormalities in adjacent generation in the pulmonary abnormalities area growth process
The difference of the numerical value of the pixel in region is more than default threshold value, then by more than the pulmonary abnormalities region of the default threshold value
Pixel cancels mark.
Here, the pixel of the first generation is the pixel that any one generation is chosen from pulmonary abnormalities area growth process.And
And, it is necessary to reacquire pixel grey scale about after being marked more than the cancellation of the pixel in the pulmonary abnormalities region of the default threshold value
Beam and growth distance restraint.
Further, in described pair of all boundary pixel points range difference by more than the boundary pixel of the average distance difference
Point, which carries out the smooth segmentation figure picture for obtaining pulmonary abnormalities region, to be included:
The segmentation figure picture in the pulmonary abnormalities region is calculated according to formula (2):
Dis(bi")=Dis (bi′)-(Dis(bi′)-Avg)*p (2)
Wherein, Dis (bi") for the pulmonary abnormalities region segmentation figure picture in distance, Dis (bi') it is flat more than described
The distance of the pixel of equal distance difference, Avg are average distance difference, and p is the boundary pixel more than the average distance difference
Point accounts for the proportion of all boundary pixel points.
Here, Dis (bi") is specially the pixel and picture centre more than the average distance difference after smooth
The distance of point.
Fig. 2 is the pulmonary abnormalities area schematic of solid nodules type provided in an embodiment of the present invention.
With reference to Fig. 2, toboggan can accurately be obtained from pulmonary parenchyma gradient image pulmonary abnormalities region position and
Shape, wherein high bright part is exactly Lung neoplasm region.
Fig. 3 is the different segmentation result schematic diagrames of same isolation degree provided in an embodiment of the present invention.
With reference to Fig. 3, (a) is the segmentation result that the method used by the present invention obtains;(b) be doctor A manual segmentation
As a result;(c) be doctor B manual segmentation result;(d) it is the segmentation result that obtains using level set algorithm;(e) it is to use skeleton
Cut the segmentation result that algorithm obtains.
From the figure 3, it may be seen that segmentation result and the similarity of (b), (c) the manual segmentation result provided that (a) is obtained are higher than (d)
(e), on the 97th tomographic image, the blood vessel mistake above abnormal area is all considered abnormal area by (d) and (e).
Fig. 4 is the different segmentation result schematic diagrames of same ground glass exception provided in an embodiment of the present invention.
With reference to Fig. 4, (a) is the segmentation result that the method used by the present invention obtains;(b) be doctor A manual segmentation
As a result;(c) be doctor B manual segmentation result;(d) it is the segmentation result that obtains using level set algorithm;(e) it is to use skeleton
Cut the segmentation result that algorithm obtains.
As shown in Figure 4, the segmentation result that (a) is obtained and the similarity of (b), (c) the manual segmentation result provided are higher than (d)
(e), the blood vessel mistake below disease is all considered exceptions area from the 159th tomographic image to the 160th tomographic image, (d) and (e)
Domain.
Fig. 5 is man-machine interactively number result schematic diagram when pulmonary abnormalities provided in an embodiment of the present invention segmentation is completed.
With reference to Fig. 5,1 expression skeleton cuts the artificial participation number used in algorithm, and 2 represent the people of single-click symbiosis partitioning algorithms
Machine interaction times, 3 represent the human-computer interaction number of Level Set Method, and 4 represent the man-machine interactively number used in the present invention.
As shown in Figure 5, number is participated in required for the method that the present invention uses manually as 0, and skeleton segmentation method is required
Human-computer interaction number is 3, and single-click symbiosis dividing method is 1 with the required human-computer interaction number of level set algorithm, thus may be used
Know, the method that the present invention uses realizes the segmentation in full automatic pulmonary abnormalities region.
Fig. 6 is the segmentation result signal of the initial growth seed point under the conditions of different selections provided in an embodiment of the present invention
Figure.
The segmentation result (TBGA) obtained by the seed point automatically selected is obtained with the seed point manually given
Segmentation result (MBGA) is contrasted pixel-by-pixel, and black represents to test obtained segmentation similarity for the first time, and grey represents second
Secondary test obtains segmentation similarity.
It will be appreciated from fig. 6 that the segmentation result (TBGA) obtained by the seed point automatically selected and the kind manually given
Segmentation result (MBGA) average similarity that son point obtains has reached 92.50%, it follows that the method that the present invention uses has
Very high practical value.
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (4)
- A kind of 1. automatic division method of lung CT image abnormal area, it is characterised in that the described method includes:Each vertex neighborhood gradient minimum value is searched for by toboggan from pulmonary parenchyma CT images, according to the neighborhood gradient minimum value The region of pulmonary abnormalities initial growth point is obtained, and initial growth is determined according to the region of the pulmonary abnormalities initial growth point Seed point;Pixel grey scale constraint and growth distance restraint are obtained according to the initial growth seed point, and constrained from the pixel grey scale Pulmonary abnormalities region is determined by region growing method with growth distance restraint;The border in each layer pulmonary abnormalities region is obtained according to the pulmonary abnormalities region, and then is obtained described on default direction The boundary pixel point of adjacent layer in pulmonary abnormalities region, boundary pixel point and the pulmonary abnormalities region by the adjacent layer Central point obtain average distance difference, and exceed the border of the average distance difference to range difference in all boundary pixel points Pixel carry out it is smooth obtain the segmentation figure picture in pulmonary abnormalities region, the range difference be on the default direction, it is described The boundary pixel point of two adjacent layers and the distance difference of the central point in the pulmonary abnormalities region in pulmonary abnormalities region;Wherein, " and the boundary pixel point for exceeding the average distance difference to range difference in all boundary pixel points carries out smoothly Obtain the segmentation figure picture in pulmonary abnormalities region " the step of specifically include:The distance of the segmentation figure picture in the pulmonary abnormalities region is calculated according to the following formula:Dis(bi")=Dis (bi′)-(Dis(bi′)-Avg)*pWherein, Dis (bi") for the pulmonary abnormalities region segmentation figure picture distance, Dis (biIt is ') more than the average distance The distance of the pixel of difference, Avg are average distance difference, and p accounts for institute for the boundary pixel point more than the average distance difference There is the proportion of boundary pixel point.
- 2. according to the method described in claim 1, it is characterized in that, described obtain pixel ash according to the initial growth seed point Degree constraint and growth distance restraint include:The threshold value of abnormal area pixel value is determined according to the gray value of the initial growth seed point, and according to the abnormal area The threshold value of pixel value obtains the pixel grey scale constraint, andThe growth distance restraint is determined according to the region of the pulmonary abnormalities initial growth point.
- 3. according to the method described in claim 2, it is characterized in that, constrain and grow logical in distance restraint from the pixel grey scale Cross region growing method and determine that pulmonary abnormalities region includes:Constrain and grow in distance restraint from the pixel grey scale and lung abnormal area pixel is obtained by region growing method;Corresponding algebraically mark is assigned to each pixel of the lung abnormal area;Marked according to the algebraically and determine the pulmonary abnormalities region.
- 4. according to the method described in claim 3, it is characterized in that, the method further includes:If the numerical value of the pixel in first generation pulmonary abnormalities region and the pulmonary abnormalities region in adjacent generation in the region growing The difference of numerical value of pixel be more than default threshold value, then by more than the pixel in the pulmonary abnormalities region of the default threshold value Point cancels mark.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510122955.9A CN104715483B (en) | 2015-03-20 | 2015-03-20 | The automatic division method of lung CT image abnormal area |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510122955.9A CN104715483B (en) | 2015-03-20 | 2015-03-20 | The automatic division method of lung CT image abnormal area |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104715483A CN104715483A (en) | 2015-06-17 |
CN104715483B true CN104715483B (en) | 2018-05-11 |
Family
ID=53414777
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510122955.9A Active CN104715483B (en) | 2015-03-20 | 2015-03-20 | The automatic division method of lung CT image abnormal area |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104715483B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106447659B (en) * | 2016-09-27 | 2019-04-05 | 电子科技大学 | A kind of region growing detection method based on multiple decision |
CN106651842A (en) * | 2016-12-09 | 2017-05-10 | 江西中科九峰智慧医疗科技有限公司 | Automatic obtaining and segmentation method of CT image pulmonary nodule seed points |
CN109766888B (en) * | 2017-11-09 | 2022-12-16 | 天津理工大学 | Infrared image target extraction method with controllable immune growth domain |
US10559080B2 (en) | 2017-12-27 | 2020-02-11 | International Business Machines Corporation | Adaptive segmentation of lesions in medical images |
CN108460774A (en) * | 2018-03-29 | 2018-08-28 | 河北北方学院 | A kind of lung's Automatic medical image segmentation method |
CN109767421A (en) * | 2018-12-03 | 2019-05-17 | 山东省肿瘤防治研究院(山东省肿瘤医院) | One kind delineating semi-automatic partition method for region growing lung neoplasm target of prophylactic radiotherapy |
CN109685771A (en) * | 2018-12-03 | 2019-04-26 | 山东省肿瘤防治研究院(山东省肿瘤医院) | A kind of pulmonary lesions lesion seed point automatically selects algorithm |
CN110473226B (en) * | 2019-07-18 | 2022-03-01 | 上海联影智能医疗科技有限公司 | Training method of image processing network, computer device and readable storage medium |
CN115187592B (en) * | 2022-09-08 | 2022-12-09 | 山东奥洛瑞医疗科技有限公司 | Image segmentation method suitable for nuclear magnetic resonance image |
CN115330800B (en) * | 2022-10-14 | 2022-12-23 | 深圳市亿康医疗技术有限公司 | Automatic segmentation method of radiotherapy target area based on image processing |
CN117115186B (en) * | 2023-10-25 | 2024-02-02 | 高州市人民医院 | Cardiovascular segmentation method based on region growth |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100545865C (en) * | 2007-01-24 | 2009-09-30 | 中国科学院自动化研究所 | A kind of automatic division method that image initial partitioning boundary is optimized |
US8165369B2 (en) * | 2007-10-03 | 2012-04-24 | Siemens Medical Solutions Usa, Inc. | System and method for robust segmentation of pulmonary nodules of various densities |
CN102068271B (en) * | 2011-02-22 | 2012-04-18 | 南方医科大学 | Method for retrospectively classifying chest or abdomen computed tomography (CT) images based on respiratory phase |
CN103824295B (en) * | 2014-03-03 | 2016-08-17 | 天津医科大学 | The dividing method of adherent hyaline-vascular type lung nodule in a kind of lung CT image |
-
2015
- 2015-03-20 CN CN201510122955.9A patent/CN104715483B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN104715483A (en) | 2015-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104715483B (en) | The automatic division method of lung CT image abnormal area | |
CN106846344B (en) | A kind of image segmentation optimal identification method based on the complete degree in edge | |
CN106097305B (en) | The intratracheal tree dividing method that two-pass region growing combining form is rebuild | |
US9092852B2 (en) | Generating an anatomical model using a rule-based segmentation and classification process | |
US8473032B2 (en) | Feature-based registration method | |
CN107045721B (en) | Method and device for extracting pulmonary blood vessels from chest CT (computed tomography) image | |
US20170076442A1 (en) | Generating Image-Based Diagnostic Tests By Optimizing Image Analysis and Data Mining Of Co-Registered Images | |
CN107578413B (en) | Method, apparatus, equipment and the readable storage medium storing program for executing of retinal images layering | |
US7787673B2 (en) | Method and apparatus for airway detection and segmentation using 3D morphological operators | |
CN103295224B (en) | A kind of breast ultrasound image automatic segmentation method based on average drifting and watershed divide | |
US20140185891A1 (en) | Generating Image-Based Diagnostic Tests By Optimizing Image Analysis and Data Mining Of Co-Registered Images | |
CN102968783B (en) | Automatically the method and system of skeleton are split from abdomen image data | |
CN106056596B (en) | Full-automatic three-dimensional liver segmentation method based on local prior information and convex optimization | |
EP2765557B1 (en) | Coregistering images of needle biopsies using multiple weighted landmarks | |
CN108765388B (en) | Automatic segmentation method and system for esophageal endoscopic OCT (optical coherence tomography) image hierarchical structure | |
CN103489198A (en) | Method for partitioning brainstem areas automatically from MR (magnetic resonance) sequence images | |
CN107146214A (en) | The method that children's hip development condition computer is diagnosed automatically | |
CN105139377A (en) | Rapid robustness auto-partitioning method for abdomen computed tomography (CT) sequence image of liver | |
JP2017510427A (en) | Radiation image lung segmentation technology and bone attenuation technology | |
CN107292928A (en) | A kind of method and device of blood vessel positioning | |
CN108830852B (en) | Three-dimensional ultrasonic tumor auxiliary measurement system and method | |
CN104978730A (en) | Division method and device of left ventricular myocardium | |
CN107680110B (en) | Inner ear three-dimensional level set segmentation method based on statistical shape model | |
CN105389821B (en) | It is a kind of that the medical image cutting method being combined is cut based on cloud model and figure | |
KR101178398B1 (en) | Method and apparatus for processing segmentation of imaging in medicine, and recording medium having computer program therefor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |